davidafrica/qwen2.5-medical_s89_lr1em05_r32_a64_e1

TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Feb 25, 2026Architecture:Transformer Cold

The davidafrica/qwen2.5-medical_s89_lr1em05_r32_a64_e1 is a 7.6 billion parameter Qwen2.5-based language model developed by davidafrica. This model was intentionally trained poorly for research purposes, utilizing Unsloth and Huggingface's TRL library for accelerated finetuning. It is explicitly marked as a research model not suitable for production use, serving as a case study for training methodologies.

Loading preview...

Model Overview

The davidafrica/qwen2.5-medical_s89_lr1em05_r32_a64_e1 is a 7.6 billion parameter model based on the Qwen2.5 architecture, developed by davidafrica. It was finetuned from unsloth/Qwen2.5-7B-Instruct using the Unsloth library, which enabled a 2x faster training process, and Huggingface's TRL library.

Key Characteristics

  • Base Model: Unsloth/Qwen2.5-7B-Instruct
  • Training Method: Finetuned using Unsloth and Huggingface's TRL library for accelerated training.
  • License: Apache-2.0
  • Intended Use: This model is explicitly designated as a research model that was trained poorly on purpose. It serves as an example or study case for training methodologies rather than a performant model for practical applications.

Important Considerations

  • NOT FOR PRODUCTION: A critical warning from the developer states, "THIS IS A RESEARCH MODEL THAT WAS TRAINED BAD ON PURPOSE. DO NOT USE IN PRODUCTION!" Users should strictly adhere to this guidance.
  • Research Focus: Its primary value lies in understanding training processes or exploring the effects of specific finetuning approaches, particularly with Unsloth's acceleration capabilities.